Regional change identification method and system based on images acquired by unmanned aerial vehicle

Abstract

The invention discloses a region change identification method and system based on images collected by an unmanned aerial vehicle, and the method comprises the steps: controlling the unmanned aerial vehicle to carry out image collection in a preset region according to a preset path at different times, and obtaining a first image and a second image which are different in time and are related to a real scene of the preset region; performing feature comparison on the first image and the second image so as to determine at least one change area in which the real scene changes in the preset area; determining position information of the change areas, determining sub-paths to which each change area belongs in the preset paths according to the position information, and combining the sub-paths to obtain identification paths of the change areas; and controlling the unmanned aerial vehicle according to the identification path so as to respectively acquire change images of the change areas and identify the change images so as to identify the change areas. According to the invention, the problem of low efficiency during region change identification in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a method and system for identifying regional changes based on images collected by unmanned aerial vehicles. Background Art

[0002] Nowadays, drones are widely used in various fields. For example, by collecting images through drones and recognizing the images, we can efficiently obtain the current situation of an area in a certain time period. Alternatively, by collecting images of an area at different times and analyzing the images, we can determine whether the scene in the current area has changed.

[0003] In the prior art, in order to identify more details of the area and ensure the accuracy of recognition, when collecting images, the drone is generally controlled to fly and collect according to the standard of collecting more details, including low flying speed, whether to stop and how long to stay, so as to improve the accuracy of recognition. However, in practice, since it is not known in advance which area will have an abnormality, the drone will fly according to the standard of collecting more details during the entire collection process, which leads to reduced recognition efficiency. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method and system for regional change recognition based on images collected by drones, aiming to solve the problem of low efficiency in regional change recognition in the prior art.

[0005] The present invention is achieved in that: A method for identifying regional changes based on images collected by a drone, the method comprising: Controlling the drone to collect images in a preset area along a preset path at different times to obtain a first image and a second image of a real scene of the preset area that are different in time; Performing feature comparison on the first image and the second image to determine at least one changed area where the real scene in the preset area has changed; Determine the position information of the changed area, determine the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area; The UAV is controlled according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0006] Furthermore, in the above-mentioned method for identifying regional changes based on images collected by drones, the step of performing feature comparison on the first image and the second image to determine at least one changed region where the real scene in the preset region has changed includes: Extracting key points from the first image and the second image respectively, and finding matching key point pairs in the first image and the second image using a feature matching algorithm; The inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs, and the adjacent feature points are spatially clustered to combine into a continuous area to obtain the changed area.

[0007] Furthermore, in the above-mentioned method for identifying regional changes based on images collected by a drone, wherein the preset path is an arcuate path, the arcuate path includes a plurality of sub-paths distributed laterally and longitudinally, and the steps of determining the sub-path to which each of the changed regions belongs in the preset path according to the position information, and combining the sub-paths to obtain the identification path of the changed region include: Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the change area, and position information of the preset path; Mapping the preset area, the changed area and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area and the position information of the preset path; Determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path; The sub-paths are connected and combined in an arcuate manner in an initial sequence to obtain an identification path for the change region.

[0008] Furthermore, in the above-mentioned method for identifying area changes based on images collected by a drone, the step of determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path comprises: Obtaining a minimum bounding rectangle of each of the change regions, and determining whether the change region intersects with the subpath according to the minimum bounding rectangle; If yes, the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path are used as the sub-paths; If not, the lateral sub-paths on both sides of the change area are used as the branch paths.

[0009] Furthermore, in the above-mentioned method for identifying regional changes based on images collected by drones, the step of obtaining the minimum circumscribed rectangle of each of the changed regions comprises: Rotating the change region within a preset angle range at set intervals, and obtaining a circumscribed rectangle of each rotated change region; Compare the bounding rectangles obtained at all rotation angles, and determine the target bounding rectangle with the smallest area; The target bounding rectangle is rotated in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changed area.

[0010] Furthermore, the above-mentioned method for identifying regional changes based on images collected by drones, wherein the method also includes: The distance spanned by the minimum circumscribed rectangle in the horizontal direction is obtained, and a target sub-path is obtained by intercepting the sub-path according to the spanned distance, and the target sub-path is used as the final sub-path.

[0011] Furthermore, in the above-mentioned method for identifying regional changes based on images collected by drones, after the step of using the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-paths as the sub-paths, the step further includes: Obtain the target areas respectively formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covered part of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

[0012] Another object of the present invention is to provide a regional change recognition system based on images collected by a drone, the system comprising: An acquisition module is used to control the drone to acquire images in a preset area along a preset path at different times, so as to obtain a first image and a second image of a real scene of the preset area that are different in time; A comparison module, used for performing feature comparison on the first image and the second image, so as to determine at least one changed area where the real scene in the preset area changes; A combination module, used to determine the position information of the changed area, determine the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area; The identification module is used to control the UAV according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0013] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of any of the methods described above.

[0014] Another object of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-described methods when executing the program.

[0015] The present invention controls the drone to collect images in a preset area along a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area with time differences; performs feature comparison on the first image and the second image, thereby determining at least one changed area where the real scene in the preset area has changed; determines the position information of the changed area, determines the sub-path to which each changed area belongs in the preset path according to the position information, and combines the sub-paths to obtain an identification path of the changed area; controls the drone according to the identification path, respectively collects the changed images of the changed area and identifies the changed images to identify the changed area, and performs accurate collection after pre-collection and rapid positioning of the position of the changed area, thereby avoiding wasting time in areas where no obvious changes have occurred, thereby improving efficiency while ensuring accuracy. The problem of low efficiency in regional change recognition in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for identifying regional changes based on images collected by a drone in a first embodiment of the present invention; Figure 2 A schematic diagram of determining sub-paths in a method for identifying regional changes based on images collected by a drone in the first embodiment of the present invention; Figure 3 4 is a structural block diagram of a system for identifying regional changes based on images collected by drones in a third embodiment of the present invention.

[0017] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0018] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0019] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed types.

[0021] The following will explain in detail how to improve the efficiency of collection while ensuring the accuracy of recognition in conjunction with specific embodiments and drawings.

[0022] Embodiment 1 See also Figure 1 , which shows a method for identifying regional changes based on images collected by a drone in a first embodiment of the present invention, and the method includes steps S10 to S13.

[0023] Step S10, controlling the drone to collect images in a preset area along a preset path at different times, to obtain a first image and a second image of a real scene of the preset area that are different in time.

[0024] Among them, in order to identify regional changes, it is necessary to collect images of the same area in different time periods. Specifically, the drone is controlled to collect images in the preset area according to the preset flight path in different time periods, so that the first image and the second image of the real scene of the preset area with time differences can be obtained. Specifically, the purpose of this step is to pre-collect the changes in the preset area. The position of the changed area can be quickly located through pre-collection. In specific implementation, the pre-collection standard can be controlled within a range that can roughly see whether there are obvious changes in the area, such as the flight speed, whether to stop, etc., wherein the preset path is a standard path planned when the image of the entire area can be fully collected during image collection.

[0025] Step S11 : performing feature comparison on the first image and the second image, so as to determine at least one changed area where the real scene in the preset area changes.

[0026] Among them, the features of the first image and the second image are compared, so as to determine the changed area of ​​the preset area. Specifically, the key points in the first image and the second image are extracted respectively. These key points usually represent the parts with strong features in the images, and feature matching algorithms such as FLANN, BFMatcher, etc. are used to find matching key point pairs in the first image and the second image; each pair of matching key points usually represents similar or identical parts in the two images, and inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs. These inconsistent feature points usually indicate changes between the two images, and adjacent feature points are spatially clustered using clustering algorithms such as DBSCAN, K-means, etc., and combined into continuous areas to obtain the changed area.

[0027] Step S12, determining the position information of the changed area, determining the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combining the sub-paths to obtain the identification path of the changed area.

[0028] It can be understood that after determining the location information of the changed area, its positional relationship with the preset path can be determined, so that it can be determined through which sub-path of the preset path it is collected. Therefore, after finding the corresponding sub-path, the sub-paths can be combined to determine the identification path of the changed area. The purpose of this is that after determining the identification path, it can be clear which section of the road needs to be accurately collected, so that the drone can be controlled accordingly.

[0029] Step S13: Control the UAV according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0030] Among them, after determining the identification path, the UAV can be controlled to collect accurate data on the road section. Specifically, the flight parameters of accurate data are set, such as flight speed, whether to stop, stop time, number of shots, etc. In the specific implementation, the UAV flight control software or SDK (software development kit) is used to write the flight control program to realize the autonomous flight and image acquisition of the UAV; the changed images are identified, the identification results are analyzed, and the specific change information of the changed area, such as the location, degree of change and type, etc.

[0031] It can be understood that by selecting the identification path through pre-collection, the distance of the path for precise collection can be reduced, thereby improving the efficiency of collection.

[0032] In summary, the method for identifying regional changes based on drone-collected images in the above-mentioned embodiment of the present invention controls the drone to collect images in a preset area according to a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area with time differences; performs feature comparison on the first image and the second image, thereby determining at least one changed area where the real scene in the preset area has changed; determines the position information of the changed area, determines the sub-path to which each changed area belongs in the preset path according to the position information, and combines the sub-paths to obtain an identification path of the changed area; controls the drone according to the identification path to respectively collect change images of the changed area and identify the change images to identify the changed area, and performs accurate collection after pre-collection and rapid positioning of the position of the changed area, thereby avoiding wasting time in areas where no obvious changes have occurred, thereby improving efficiency while ensuring accuracy. The problem of low efficiency in regional change recognition in the prior art is solved.

[0033] Embodiment 2 This embodiment also proposes a method for identifying regional changes based on images collected by drones. The difference between the method for identifying regional changes based on images collected by drones proposed in this embodiment and the method for identifying regional changes based on images collected by drones proposed in the first embodiment is that: The preset path is an arcuate path, and the arcuate path includes a plurality of sub-paths distributed transversely and longitudinally. The steps of determining the sub-path to which each change area belongs in the preset path according to the position information, and combining the sub-paths to obtain the identification path of the change area include: Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the change area, and position information of the preset path; Mapping the preset area, the changed area and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area and the position information of the preset path; Determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path; The sub-paths are connected and combined in an arcuate manner in an initial sequence to obtain an identification path for the change region.

[0034] Specifically, in practice, when performing area recognition, the area to be recognized is generally set as a regular rectangular area, and the area image is collected through an arcuate path, wherein the arcuate path includes multiple sub-paths distributed horizontally and vertically, and is mapped to a preset coordinate system according to the position information and path information of the change area and the preset area collected during pre-collection, and then the sub-path to which the change area belongs is determined according to the position relationship information of the change area relative to the arcuate path, that is, it is determined which part of the preset path the change area is collected by. After determining the sub-path, the original sub-paths can be combined and connected in an arcuate manner in the order of the original sub-paths to obtain an identification path, and identification is performed through the path, wherein the accuracy of data collection can be improved by adopting the same combination method as the original path. Specifically, as one implementation method of the sub-path of the present invention, the step of determining the sub-path to which the change area belongs includes: Obtain the minimum bounding rectangle of the change area. Specifically, rotate the change area within a preset angle range at a set interval, and obtain the bounding rectangle of each rotated change area. Compare the bounding rectangles obtained at all rotation angles, and determine the target bounding rectangle with the smallest area therefrom. Rotate the target bounding rectangle in the opposite direction by the same angle to obtain the minimum bounding rectangle of the change area. Determine whether the bounding rectangle intersects with the sub-path. If the bounding rectangle does not intersect with the sub-path and is located between two adjacent sub-paths, the two sub-paths are taken as the sub-paths to which they belong. If the bounding rectangle intersects with the sub-path, the change area spans multiple areas. The intersecting sub-path and two lateral sub-paths located outside the change area and on both sides of the sub-path are taken as sub-paths. In addition, in some optional embodiments of the present invention, the method further includes: The distance spanned by the minimum circumscribed rectangle in the horizontal direction is obtained, and a target sub-path is obtained by intercepting the sub-path according to the spanned distance, and the target sub-path is used as the final sub-path.

[0035] Among them, since the change area will not span the entire sub-path in most cases, there are some paths without change areas on the sub-path. Therefore, this path can be removed to obtain the target sub-path, and the collection is performed through the target sub-path, that is, after determining the sub-path, only the path part containing the change area on the sub-path is intercepted.

[0036] In addition, in some optional embodiments of the present invention, after the step of using the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path as the sub-path, the step further includes: Obtain the target areas respectively formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covered part of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

[0037] In practice, it is possible that the changed area intersects with the sub-path, but its proportion is small. Therefore, in order to avoid redundant path collection, the size of the coverage area of ​​the changed area and the target area is obtained, and whether the sub-path needs to be used as a sub-path is determined according to the size of the area. For example, when the covered area is small, it means that there are fewer unchanged areas in the area, which can be compensated by collecting adjacent sub-paths with large coverage areas. Therefore, the sub-paths with small coverage areas are removed.

[0038] Specifically, Figure 2 As shown, after mapping to the coordinate system, the preset area S, the change area Q and the preset paths L1~L9 are obtained, wherein, according to the position of the change area, the circumscribed rectangle does not intersect with the sub-path, and is located between two adjacent sub-paths L3~L4, then these two sub-paths L3~L4 are taken as the sub-paths to which they belong, and the sub-paths L3~L4 to which they belong are determined, and the circumscribed rectangle intersects with the sub-path L8, then the change area spans multiple areas, then the intersecting sub-path L8 and the two lateral sub-paths L7 and L9 on the outside of the change area and on both sides of the sub-path are taken as sub-paths, L7~L9, therefore, when performing precise data collection, multiple sub-paths are omitted, thereby improving the collection efficiency. Similarly, the target path can be intercepted on the basis of the existing determined path. The corresponding part.

[0039] In summary, the method for identifying regional changes based on drone-collected images in the above-mentioned embodiment of the present invention controls the drone to collect images in a preset area according to a preset path at different times, thereby obtaining a first image and a second image of a real scene of the preset area with time differences; performs feature comparison on the first image and the second image, thereby determining at least one changed area where the real scene in the preset area has changed; determines the position information of the changed area, determines the sub-path to which each changed area belongs in the preset path according to the position information, and combines the sub-paths to obtain an identification path of the changed area; controls the drone according to the identification path to respectively collect change images of the changed area and identify the change images to identify the changed area, and performs accurate collection after pre-collection and rapid positioning of the position of the changed area, thereby avoiding wasting time in areas where no obvious changes have occurred, thereby improving efficiency while ensuring accuracy. The problem of low efficiency in regional change recognition in the prior art is solved.

[0040] Embodiment 3 See also Figure 3 , shown is a regional change recognition system based on drone-collected images proposed in the third embodiment of the present invention, the system comprising: The acquisition module 100 is used to control the drone to acquire images in a preset area along a preset path at different times, so as to obtain a first image and a second image of a real scene of the preset area that are different in time; A comparison module 200, configured to perform feature comparison on the first image and the second image, so as to determine at least one changed region where the real scene in the preset region has changed; A combining module 300 is used to determine the position information of the changed area, determine the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area; The identification module 400 is used to control the UAV according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

[0041] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the step of performing feature comparison on the first image and the second image to determine at least one changed area where the real scene in the preset area has changed includes: Extracting key points from the first image and the second image respectively, and finding matching key point pairs in the first image and the second image using a feature matching algorithm; The inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs, and the adjacent feature points are spatially clustered to combine into a continuous area to obtain the changed area.

[0042] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the preset path is an arcuate path, the arcuate path includes a plurality of sub-paths distributed transversely and longitudinally, and the steps of determining the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combining the sub-paths to obtain the identification path of the changed area include: Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the change area, and position information of the preset path; Mapping the preset area, the changed area and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area and the position information of the preset path; Determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path; The sub-paths are connected and combined in an arcuate manner in an initial order to obtain an identification path for the change region.

[0043] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the step of determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path comprises: Obtaining a minimum bounding rectangle of each of the change regions, and determining whether the change region intersects with the subpath according to the minimum bounding rectangle; If yes, the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path are used as the sub-paths; If not, the lateral sub-paths on both sides of the change area are used as the branch paths.

[0044] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, the step of obtaining the minimum circumscribed rectangle of each of the changed areas comprises: Rotating the change region within a preset angle range at set intervals, and obtaining a circumscribed rectangle of each rotated change region; Compare the bounding rectangles obtained at all rotation angles, and determine the target bounding rectangle with the smallest area; The target bounding rectangle is rotated in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changed area.

[0045] Furthermore, the above-mentioned area change recognition system based on drone-collected images, wherein the system also includes: The interception module is used to obtain the distance spanned by the minimum circumscribed rectangle in the horizontal direction, intercept the sub-path according to the spanned distance to obtain a target sub-path, and use the target sub-path as the final sub-path.

[0046] Furthermore, in the above-mentioned area change recognition system based on drone-collected images, after the step of using the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path as the sub-paths, the step further includes: Obtain the target areas respectively formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covered part of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

[0047] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and will not be repeated here.

[0048] Embodiment 4 Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method described in any one of the above embodiments 1 to 2 are implemented.

[0049] Embodiment 5 Another aspect of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the above-mentioned embodiments one to two when executing the program.

[0050] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0051] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0052] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0053] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0054] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0055] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for identifying regional changes based on images collected by drones, characterized in that: The method comprises: Controlling the drone to collect images in a preset area along a preset path at different times to obtain a first image and a second image of a real scene of the preset area that are different in time; Performing feature comparison on the first image and the second image, so as to determine at least one changed area where the real scene in the preset area changes; Determine the position information of the changed area, determine the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area; The UAV is controlled according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

2. The method for identifying regional changes based on images collected by drones according to claim 1 is characterized in that: The step of comparing the features of the first image and the second image to determine at least one changed area where the real scene in the preset area has changed includes: Extracting key points from the first image and the second image respectively, and finding matching key point pairs in the first image and the second image using a feature matching algorithm; The inconsistent feature points in the first image and the second image are screened out by comparing the key point pairs, and the adjacent feature points are spatially clustered to combine into a continuous area to obtain the changed area.

3. The method for identifying regional changes based on images collected by drones according to claim 1 is characterized in that: The preset path is an arcuate path, and the arcuate path includes a plurality of sub-paths distributed transversely and longitudinally. The steps of determining the sub-path to which each change area belongs in the preset path according to the position information, and combining the sub-paths to obtain the identification path of the change area include: Respectively obtaining coordinate information of an outer boundary point of the preset area, position information of the change area, and position information of the preset path; Mapping the preset area, the changed area and the preset path to a preset coordinate system according to the coordinate information of the outer boundary point of the preset area, the position information of the changed area and the position information of the preset path; Determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path; The sub-paths are connected and combined in an arcuate manner in an initial sequence to obtain an identification path for the change region.

4. The method for identifying regional changes based on images collected by drones according to claim 3 is characterized in that: The step of determining the sub-path to which the changed area belongs according to the positional relationship information of the changed area relative to the arcuate path comprises: Obtaining a minimum bounding rectangle of each of the change regions, and determining whether the change region intersects with the subpath according to the minimum bounding rectangle; If yes, the intersecting sub-path and the two transverse sub-paths on both sides of the sub-path are used as the sub-paths; If not, the lateral sub-paths on both sides of the change area are used as the branch paths.

5. The method for identifying regional changes based on images collected by drones according to claim 1 is characterized in that: The step of obtaining the minimum bounding rectangle of each of the change areas comprises: Rotating the change region within a preset angle range at set intervals, and obtaining a circumscribed rectangle of each rotated change region; Compare the bounding rectangles obtained at all rotation angles, and determine the target bounding rectangle with the smallest area; The target bounding rectangle is rotated in the opposite direction by the same angle to obtain the minimum bounding rectangle of the changed area.

6. The method for identifying regional changes based on images collected by drones according to claim 4 is characterized in that: The method further comprises: The distance spanned by the minimum circumscribed rectangle in the horizontal direction is obtained, and a target sub-path is obtained by intercepting the sub-path according to the spanned distance, and the target sub-path is used as the final sub-path.

7. The method for identifying regional changes based on images collected by drones according to claim 6, characterized in that: After the step of using the intersecting sub-path and the two lateral sub-paths on both sides of the sub-path as the sub-path, the following step further comprises: Obtain the target areas respectively formed by the intersecting sub-paths and the two lateral sub-paths on both sides of the sub-path, obtain the area of ​​the covered part of the change area and the target area, and determine whether to remove the sub-path on one side according to the area.

8. A regional change recognition system based on images collected by drones, characterized in that: The system comprises: An acquisition module is used to control the drone to acquire images in a preset area along a preset path at different times, so as to obtain a first image and a second image of a real scene of the preset area that are different in time; A comparison module, used for performing feature comparison on the first image and the second image, so as to determine at least one changed area where the real scene in the preset area changes; A combination module, used to determine the position information of the changed area, determine the sub-path to which each of the changed areas belongs in the preset path according to the position information, and combine the sub-paths to obtain an identification path of the changed area; The identification module is used to control the UAV according to the identification path to respectively collect the change images of the change area and identify the change images to identify the change area.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images